GradientAI Platform Features

GradientAI Platform is a comprehensive suite of tools and features designed to help you build, manage, and deploy AI-powered agents. This includes a variety of foundation models to choose from and a range of features to make your agents more effective and efficient, including agent routing, knowledge bases, guardrails, and more.

Agents

Agents are AI-powered tools that can perform a wide range of tasks, like answering questions or generating text content. Agents can use a combination of foundation models, knowledge bases, functions, and guardrails to inform their responses to user queries.

You can interact with agents in the following ways:

• Agent endpoints: Each agent has an endpoint that allows you to interact with it through an API. You can integrate endpoints into your applications, customize requests to the agent, and authenticate them using access keys.

• Chatbot embed: We provide a code snippet for each agent that allow you to embed a chatbot interface into your website or application.

• Agent playground: We provide a web-based interface for interacting with agents, allowing you to test and refine agents.

• Agent Tracing: View a detailed step-by-step timeline of how your agent processes prompts, including token usage, processing time, and resource access. If you’ve opted in to storing interaction data, each trace also includes the full input and output for every interaction, giving you a complete record of the conversation flow. Use this information to troubleshoot issues, improve agent performance, and reduce costs.

• Agent templates: We provide templates for common use cases, such as a customer support and business analysis. Templates have predefined instructions and foundation models that allow you to quickly create an agent.

Models

Models are large language models (LLMs) trained on large datasets to perform a variety of tasks. You can choose from multiple foundation models, including commercial and open-source options, depending on your use case. These models generate responses for agents or respond directly to requests without creating an agent.

You can interact with models in the following ways:

• Model playground: Test and compare model performance in a web-based interface. You can adjust settings like temperature and token limits, evaluate model responses, and fine-tune how your agents behave.

• Serverless Inference: Send API requests directly to foundation models without creating or managing an agent. Serverless inference runs requests immediately using your model access key and model slug with no need to define instructions or context ahead of time.

Agent Evaluations

Agent evaluations are automated tests that can provide insight into how well your agents are responding to prompts you’ve provided. Workspaces let you run evaluations on multiple agents at once.

There are 19 evaluation metrics available you can use to evaluate your agents, incluidng checking for factual correctness, instruction adherence, tone, and toxicity.

The test results are percentage pass/fail scores with visualizations so you can see your agents’ performance over time.

RAG Pipelines and Knowledge Bases

A knowledge base is a private repository of unstructured files, folders, or web pages that enhances agent responses through retrieval-augmented generation (RAG). When you attach a knowledge base to an agent, it can retrieve and use relevant information even if the foundation model wasn’t originally trained on it. Knowledge bases can include documentation, FAQs, and guides to help the agent deliver more accurate, context-aware responses.

Knowledge bases store raw data in DigitalOcean Spaces object storage and index it with a DigitalOcean OpenSearch cluster. After indexing, you can attach the knowledge base to an agent to deliver more accurate and relevant responses to user queries.

We offer different vector embedding models that allow you to choose a model that best captures the context of your data. Vector embeddings models organize and find patterns in unstructured data, allowing your agents to search for content that matches the user’s input.

Guardrails

Guardrails scan an agent’s input and output for sensitive and inappropriate content and override the agent’s output when it detects the specified problematic content. For example, they help prevent an agent from sharing login credentials or credit card information when tuned correctly for your specific use case.

We offer the following guardrails that you can attach to your agent:

• Sensitive Data: Identifies and anonymizes various categories of sensitive information, including credit card numbers, personally identifiable information, and location data.

• Jailbreak: Helps your agent maintain proper functionality by preventing malicious inputs.

• Content Moderation: Controls agent output by filtering responses related to inappropriate content categories, including violence and hate, sexual content, weapons, regulated substances, self-harm, and illegal activities.

Agent and Function Routing

You can use agent and function routing to create more complex and dynamic responses to user queries.

• Agent Routing directs queries to the right agent based on context.

• Function Routing enhances agent responses with real-time or external data.

For example, say you have one agent for general travel questions and another for managing booking. Agent routing autoamtically sends a user request for booking to the booking agent for a more accurate response. Function routing can call a function to retrieve weather information that the booking agent can include in its reply to offer more relevant travel recommendations.